พื้นฐาน Series และ DataFrame

แพนดาสคืออะไร

import pandas as pd

s = pd.Series([10, 20, 30], index=["a","b","c"])
print(s)
# a    10
# b    20
# c    30

การสร้าง Series

import pandas as pd

# From list:
s1 = pd.Series([1, 2, 3])

# From dict (keys become index):
s2 = pd.Series({"x": 10, "y": 20})

# Scalar (broadcast):
s3 = pd.Series(5, index=range(4))
print(s3)   # 0 5 / 1 5 / 2 5 / 3 5

การสร้าง DataFrame

import pandas as pd

df = pd.DataFrame({
    "name": ["Alice","Bob","Carol"],
    "age":  [30, 25, 35],
    "score":[95.5, 87.0, 92.3]
})
print(df)

การตรวจสอบพื้นฐาน

import pandas as pd

df = pd.read_csv("data.csv")
print(df.head())       # first 5 rows
print(df.shape)        # (rows, cols)
print(df.dtypes)       # column types
print(df.describe())   # count, mean, std, min...

การเข้าถึงคอลัมน์

import pandas as pd

df = pd.DataFrame({"age":[30,25], "city":["NY","LA"]})
print(df["age"])       # preferred
print(df.age)          # also works if name is simple
print(df[["age","city"]])  # multiple columns

พื้นฐานดัชนี

import pandas as pd

df = pd.DataFrame({"val":[10,20,30]}, index=["a","b","c"])
print(df.loc["b"])     # row with label b
print(df.index)        # Index(['a','b','c'])

# Reset to default integer index:
df.reset_index(drop=True, inplace=True)

การเพิ่มและนำคอลัมน์ออก

import pandas as pd

df = pd.DataFrame({"a":[1,2,3],"b":[4,5,6]})
df["c"] = df["a"] + df["b"]   # new column
df.drop(columns=["b"], inplace=True)
print(df)

การจัดแนว Series

import pandas as pd

s1 = pd.Series([1,2,3], index=["a","b","c"])
s2 = pd.Series([10,20], index=["b","c"])
print(s1 + s2)
# a     NaN
# b    12.0
# c    23.0

to_dict และ to_list

import pandas as pd

df = pd.DataFrame({"x":[1,2],"y":[3,4]})
print(df.to_dict("records"))
# [{'x': 1, 'y': 3}, {'x': 2, 'y': 4}]

print(df["x"].to_list())
# [1, 2]

การอ่านไฟล์

import pandas as pd

df_csv    = pd.read_csv("data.csv")
df_excel  = pd.read_excel("data.xlsx", sheet_name="Sheet1")
df_json   = pd.read_json("data.json")
df_parq   = pd.read_parquet("data.parquet")
# pd.read_sql("SELECT * FROM table", conn)

การเขียนไฟล์

import pandas as pd

df = pd.DataFrame({"a":[1,2],"b":[3,4]})
df.to_csv("out.csv", index=False)
df.to_json("out.json", orient="records")
df.to_parquet("out.parquet")

ตรวจสอบด่วน

ทบทวน